© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14484
    Prev
    Next
    INDEX
    Explanations

    Ru/ruch

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Better
    0.66
     Better
    0.63
     better
    0.61
    better
    0.55
     bedre
    0.52
     BETTER
    0.52
     bättre
    0.52
    請
    0.52
    বিস্তারিত
    0.50
     Fundamental
    0.50
    POSITIVE LOGITS
     ru
    0.65
     RU
    0.65
     rufo
    0.65
     ruim
    0.64
     Rupert
    0.63
     roused
    0.63
     Ruf
    0.63
     Ру
    0.62
     Ruk
    0.61
    Ru
    0.59
    Activations Density 0.033%

    No Known Activations